Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11267
    Prev
    Next
    INDEX
    Explanations

    technical terms and names related to software installation and system management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.05
    2:0.06
    3:0.05
    4:0.04
    5:0.03
    6:0.16
    7:0.03
    8:0.03
    9:0.39
    10:0.02
    11:0.05
    Negative Logits
     Feldman
    -3.42
     Cohn
    -3.12
     Fitzgerald
    -3.12
     gri
    -3.08
     rake
    -3.08
    zilla
    -3.06
    Dick
    -3.05
     Daly
    -3.05
     Manit
    -3.00
     Chandler
    -2.94
    POSITIVE LOGITS
     Bun
    6.23
    UN
    5.91
    uns
    5.57
    un
    5.51
     UN
    5.25
    uno
    5.13
     Nun
    4.79
    unts
    4.68
     bun
    4.64
    una
    4.46
    Activations Density 0.023%

    No Known Activations